{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-the-importance-of-cross-task-features-for","title":"On the importance of cross-task features for class-incremental learning","arxiv_id":"2106.11930","date":"2021-06-22","proceeding":null,"authors":["Albin Soutif--Cormerais","Marc Masana","Joost Van de Weijer","Bartłomiej Twardowski"],"abstract":"In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform cross-task discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of cross-task features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features, and the knowledge transfer between tasks. This is especially important when tasks contain limited amount of data.","url_abs":"https://arxiv.org/abs/2106.11930v4","url_pdf":"https://arxiv.org/pdf/2106.11930v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-the-importance-of-cross-task-features-for","repo_url":"https://github.com/AlbinSou/cross_task_cil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.11930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11930"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/AlbinSou/cross_task_cil","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"dc430dd8ca7f26e9","entry":"extract_forgetting","repo":"AlbinSou/cross_task_cil","repo_kind":"official","path":"src/cumulative_metrics.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/cumulative_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc430dd8ca7f26e9"}},{"code_sha256_prefix":"544cf571f3a07cc3","entry":"get_data","repo":"AlbinSou/cross_task_cil","repo_kind":"official","path":"src/datasets/base_dataset.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/datasets/base_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"544cf571f3a07cc3"}},{"code_sha256_prefix":"2125ab30557c552f","entry":"get_datasets","repo":"AlbinSou/cross_task_cil","repo_kind":"official","path":"src/datasets/data_loader.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/datasets/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2125ab30557c552f"}},{"code_sha256_prefix":"00e4bb5fb503e035","entry":"get_loaders","repo":"AlbinSou/cross_task_cil","repo_kind":"official","path":"src/datasets/data_loader.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/datasets/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00e4bb5fb503e035"}},{"code_sha256_prefix":"7210d296e5161f2a","entry":"get_transforms","repo":"AlbinSou/cross_task_cil","repo_kind":"official","path":"src/datasets/data_loader.py","file_url":"https://github.com/AlbinSou/cross_task_cil/blob/HEAD/src/datasets/data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7210d296e5161f2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}